qwenlong-long-context-reasoning

【数据与研究】Systematically post-train models for long-context reasoning through multi-hop data synthesis, stabilized RL with adaptive entropy control, and memory-augmented architecture supporting 4M+ token sequences. Achieves performance comparable to GPT-5 and Gemini-2.5-Pro on long-context benchmarks.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准